PNNL

Abstract

Server applications with adaptive behaviors can adapt their functionality in response to environmental changes, and significantly reduce the on-going costs of system deployment and administration. However, developing adaptive server applications is challenging due to the complexity of server technologies and highly dynamic application environments. This paper presents an architecture framework, known as the Adaptive Server Framework (ASF). ASF provides a clear separation between the implementation of adaptive behaviors and the server application business logic. This means a server application can be cost effectively extended with programmable adaptive features through the definition and implementation of control components defined in ASF. Further-more, ASF is a lightweight architecture in that it incurs low CPU overhead and memory usage. We demonstrate the effectiveness of ASF through a case study, in which a server application dynamically determines the resolution and quality to scale an image based on the load of the server and network connection speed. The experimental evaluation demonstrates the performance gains possible by adaptive behaviors and the low overhead introduced by ASF.